Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 944 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5048. Min Range: -6.5048
Max Act: 6.5048. Min Act: -0.1700
Data Index: 6237146 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5048. Min Range: -6.5048
Max Act: 6.4735. Min Act: -0.1700
Data Index: 4533192 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5048. Min Range: -6.5048
Max Act: 6.4110. Min Act: -0.1700
Data Index: 6248315 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5048. Min Range: -6.5048
Max Act: 6.4110. Min Act: -0.1700
Data Index: 3617866 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5048. Min Range: -6.5048
Max Act: 6.3485. Min Act: -0.1700
Data Index: 8703348 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5048. Min Range: -6.5048
Max Act: 6.3173. Min Act: -0.1700
Data Index: 6495890 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5048. Min Range: -6.5048
Max Act: 6.3485. Min Act: -0.1700
Data Index: 7703498 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5048. Min Range: -6.5048
Max Act: 6.2860. Min Act: -0.1700
Data Index: 3025597 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5048. Min Range: -6.5048
Max Act: 6.2548. Min Act: -0.1700
Data Index: 3206985 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5048. Min Range: -6.5048
Max Act: 6.2235. Min Act: -0.1700
Data Index: 5520247 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5048. Min Range: -6.5048
Max Act: 6.2235. Min Act: -0.1700
Data Index: 7479635 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5048. Min Range: -6.5048
Max Act: 6.1923. Min Act: -0.1700
Data Index: 5672522 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5048. Min Range: -6.5048
Max Act: 6.1298. Min Act: -0.1700
Data Index: 926852 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5048. Min Range: -6.5048
Max Act: 6.1923. Min Act: -0.1700
Data Index: 6687301 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5048. Min Range: -6.5048
Max Act: 6.1298. Min Act: -0.1700
Data Index: 2933412 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5048. Min Range: -6.5048
Max Act: 6.0673. Min Act: -0.1700
Data Index: 108075 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5048. Min Range: -6.5048
Max Act: 6.0673. Min Act: -0.1700
Data Index: 2250688 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5048. Min Range: -6.5048
Max Act: 6.0673. Min Act: -0.1700
Data Index: 2966941 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5048. Min Range: -6.5048
Max Act: 6.0360. Min Act: -0.1700
Data Index: 4426442 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5048. Min Range: -6.5048
Max Act: 6.0360. Min Act: -0.1700
Data Index: 928915 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #19